AI Engineer · Healthcare AI Researcher

Nasim Mahmud
Nayan

Currently Deputy Manager, AI & ML · BRAC Technology Division

Building trustworthy AI that democratizes medical care, education, and business — through rigorous research and production engineering.

Google Scholar → Get in touch Download CV
Nasim Mahmud Nayan
13
Publications
159
Citations
6
h-index
4+
Years in AI / ML
10k+
Students Reached
01

About

Research depth meets
production engineering

I work across both research and industry — combining academic rigour with hands-on engineering, from the M-TRUST fairness toolkit to production platforms used by thousands.

I am drawn to problems where accuracy alone is not enough — systems that demand transparency, fairness, and real-world reliability. My focus spans multimodal medical AI, bias mitigation, LLM & RAG clinical decision support, and scalable ML for everyday use.

Growing up in rural Bangladesh, where healthcare access was limited, I saw firsthand the need to democratize medical care and education. That experience led me to found OgroPath, an AI platform making medical entrance-exam preparation accessible to students nationwide.

Research Focus

ATrustworthy & Fair Medical AI

Bias detection and mitigation across demographic, annotation, and amplification axes in clinical models.

BMultimodal Diagnostics

Combining imaging, signals, and clinical text for explainable disease prediction and screening.

CLLM & RAG Decision Support

Citation-grounded retrieval, fact-checking, and source attribution for clinical and enterprise QA.

DMedical Cyber-Physical Systems

IoT-enabled, privacy-preserving pipelines for maternal health and remote monitoring.

02

Selected Publications

13 papers · 159 citations
h-index 6 · i10 4
01

A Medical Cyber-Physical System for Predicting Maternal Health in Developing Countries Using Machine Learning

M. M. Hossain, M. A. Kashem, N. M. Nayan, M. A. Chowdhury · Healthcare Analytics, 2024
67
Cites
02

SMOTE Oversampling and Near-Miss Undersampling Based Diabetes Diagnosis from Imbalanced Dataset with XAI Visualization

N. M. Nayan, A. Islam, M. U. Islam, E. Ahmed, M. M. Hossain, M. Z. Alam · IEEE ISCC, 2023
23
Cites
03

Date Fruit Classification with Machine Learning and Explainable Artificial Intelligence

M. Sahidullah, N. M. Nayan, M. S. Morshed, M. M. Hossain, M. U. Islam · Int'l Journal of Computer Applications, 2023
19
Cites
04

An IoT-Based Real-Time Environmental Monitoring System for Developing Areas

M. Alam, M. M. Islam, N. M. Nayan, J. Uddin · J. of Advanced Research in Applied Sciences & Engineering Tech., 2024
18
Cites
05

Artificial Intelligence-Driven Approach for Predicting Maternal Health Risk Factors

M. M. Hossain, M. A. Kashem, N. M. Nayan · 9th SEEDA-CECNSM, Athens, 2024
9
Cites
06

An Interpretable and Balanced Machine Learning Framework for Parkinson's Disease Prediction Using Feature Engineering and Explainable AI

N. M. Nayan, A. M. Rana, M. M. Islam, J. Uddin, T. Yasmin, J. Uddin · PLOS ONE, 2025
7
Cites
07

Investigation of Air Effluence Using IoT and Machine Learning

S. U. P. Shakil, M. A. Kashem, M. M. Islam, N. M. Nayan, J. Uddin · Int'l Conf. for Emerging Technologies in Computing, 2023
6
Cites
08

Air Pollution Monitoring Using IoT and Machine Learning in the Perspective of Bangladesh

M. M. Islam, S. U. P. Shakil, N. M. Nayan, M. A. Kashem, J. Uddin · Annals of Emerging Technologies in Computing (AETiC), 2024
5
Cites
09

Recent Advancements of Computer Vision in Healthcare: A Systematic Review

M. Islam, N. M. Nayan, A. Islam, S. Sikder, M. R. Rashel, M. Z. Alam · IEIE Transactions on Smart Processing & Computing, 2024
4
Cites
10

Enhancing the Security of Pregnancy Health Data Transmission through Homomorphic Encryption: An Advanced Model

M. M. Hossain, N. M. Nayan, M. A. Kashem · Internet of Things Applications and Technology, 2024
1
Cites
11

A Comprehensive Maternal Health Risk Prediction Dataset from IoT-Enabled Medical Cyber-Physical Systems in Developing Countries

M. M. Hossain, N. M. Nayan, M. A. Kashem · BMC Medical Informatics and Decision Making, 2026
Published
12

Designing an AI-Driven Logistics Planning Artifact for Constraint-Aware Vehicle Routing

M. U. Islam, N. M. Nayan, F. Ayeni, S. Okuboyejo · 2026
2026
View full list on Google Scholar →
03

Research Experience

3 labs · medical AI,
CV & IoT systems
Jul 2022 – Present
Medical Cyber-Physical Systems
Shanto-Mariam University of Creative Technology
Advisors — Prof. Mohammad Mobarak Hossain · Dr. Jasim Uddin

Research Assistant — Medical CPS

  • Architected an ensemble framework for maternal-health risk stratification reaching 99% accuracy and cutting algorithmic bias 34% across 5,000+ records.
  • Implemented homomorphic encryption on IoT devices for secure, compliant pregnancy-data transmission.
  • Co-authored 3 papers in high-impact venues (combined 50+ citations).
Aug 2022 – Mar 2023
Healthcare AI & IoT Systems
Rising Research Lab
Advisors — Md. Monirul Islam · Dr. Jia Uddin

Research Assistant — Healthcare AI & IoT

  • Deployed a multi-disease prediction system (diabetes, Parkinson's, maternal health) at 92% average accuracy with a 5-location IoT air-quality network.
  • Engineered a full pipeline from IoT capture to real-time inference.
  • Built an AutoML pipeline that cut model-development time 60% while maintaining performance.
Jan 2023 – Dec 2024
Computer Vision in Medicine
EMPATHY Lab, Independent University Bangladesh
Advisors — Dr. Ashraful Islam · Dr. Muhammad Usama Islam

Research Assistant — Computer Vision

  • Conducted a systematic review of 125+ papers on healthcare computer vision, mapping key gaps and opportunities.
  • Analyzed CNNs and Vision Transformers for medical imaging and predictive analytics.
  • Synthesized findings to steer lab direction in surgical assistance and remote monitoring.
Current Work — In Progress
In Progress

M-TRUST Enhancement

Advancing the medical-AI fairness toolkit with new bias-detection algorithms and broader healthcare dataset support.

Targeting JMIR / IEEE TBME · FairnessML · PyTorch
In Progress

ECG Arrhythmia Detection

Deep-learning model for automated ECG interpretation detecting 5 cardiac conditions with 96% accuracy.

Biomedical Signal Processing · PyTorch · CNN
In Progress

Chest X-Ray Diagnosis System

Vision-transformer multi-disease classification from radiographs with explainable AI and radiologist validation.

Nature Scientific Reports · ViT · XAI
04

Key Projects

Open-source toolkits &
production AI systems

M-TRUST

Open Source

Plug-in Python toolkit to detect and mitigate demographic, quality, annotation, and amplification bias in clinical AI — one-line wrapper API with docs and reproducible examples.

30.8%
Bias reduced
4-axis
Bias coverage
PythonPyTorchScikit-learnPandasMatplotlib

ExplainRAG-FC-AS

Clinical RAG

Clinical decision support via RAG & LLMs with thematic clustering and NLI fact-checking before generation — source-level attribution for traceable, transparent recommendations.

<10s
Query time
90%
Clinician pref.
0.85
Evidence conf.
FAISSK-MeansRoBERTa-MNLIGPT-4Streamlit

Trustworthy ECG Platform

Edge AI

Real-time and offline ECG analysis with fairness-aware training and uncertainty estimation — supports live sensor streams and digitized paper ECGs with natural-language explanations.

>0.9
Fairness score
95%
Accuracy
<100ms
Edge inference
PyTorchResNetSciPyStreamlit

Multimodal Chest X-Ray Diagnosis

Bias Analysis

Combined CheXNet image features with BioBERT clinical text to classify 14 thoracic diseases — diagnosed 4.3× cross-modal bias amplification and added Grad-CAM explanations for clinician trust.

14
Diseases
7.6→4.5%
Disparity cut
TorchVisionBioBERTGrad-CAMDocker

RAG-Based Website Generator

Cost-Efficient AI

AI website generator using RAG to assemble pre-built React components instead of generating code from scratch — with PostgreSQL + pgvector semantic search and tree-sitter AST parsing.

92%
Token reduction
94%
Cost savings
FastAPIpgvectorNext.jsGPT-4otree-sitter

Bengali Literature RAG

Retrieval

RAG pipeline combining LaBSE embeddings with BM25 keyword search via Reciprocal Rank Fusion, with selective GPT-4o-Mini enhancement based on retrieval confidence.

95%
Hit@5
32ms
Response
60%
Cost cut
LaBSEBM25GPT-4o MiniFastAPIDocker
05

Industry & Entrepreneurship

Enterprise AI strategy
to founder-led products

BRAC — Technology Division

Deputy Manager, AI & Machine Learning
May 2026 – Present
  • Lead enterprise AI and analytics initiatives, translating organizational challenges into scalable solutions.
  • Design analytics architectures, AI workflows, and schema structures for Cloudera-based ecosystems.
  • Coordinate AI vendors, engineering teams, and stakeholders across planning, alignment, and delivery.
Enterprise AIGenAIClouderaAI GovernanceBI

Solyntra Limited

AI Engineer
Dec 2025 – Apr 2026
  • Led R&D and architecture for SaaS AI knowledge systems with citation-grounded RAG pipelines.
  • Implemented metadata-aware ingestion, hybrid retrieval, and a 'No Source, No Result' grounding policy.
  • Performed parameter-efficient LLM fine-tuning with LoRA (PEFT) and multi-agent architecture.
LLMsRAGLoRAHugging FaceFastAPIPostgreSQL

Programming Hero

Machine Learning Engineer (Remote)
Dec 2023 – Sep 2025
  • Built the Zenyora AI wellness platform (Microsoft Store) with real-time posture detection at 95% accuracy and sub-100ms inference, serving 100+ daily users.
  • Architected a voice-enabled RAG real-estate sales assistant over 2,000+ listings at 95% query relevance using Whisper STT and ElevenLabs TTS.
PyTorchOpenCVLangChainPineconeGPT-4Docker

Primacy Infotech Ltd

AI Engineer
Jul 2023 – Nov 2023
  • Led an AI tour planner for 6 UNESCO sites, cutting itinerary creation from 2 hours to 5 minutes.
  • Built a clustering pipeline over 5,000+ visitor surveys, raising satisfaction scores 35%.
GPT-3.5FastAPIPostgreSQLDockerStreamlit
★

Featured Venture

Founder & Lead AI Engineer
Apr 2025 – Present

OgroPath

AI-Powered Medical Exam Prep Platform
Founder & Lead Engineer

Founded to democratize medical education for students across Bangladesh, especially in underserved rural communities. OgroPath combines NLP-based question generation with adaptive learning to make medical entrance exam preparation accessible to all.

AI Question GeneratorNLP-powered from PDFs
21K+ QuestionsComprehensive bank
Adaptive LearningPersonalized study plans
National RankingReal-time system
21k+
Questions
10k+
Students
Active
Platform
LLMsNLPFastAPIPostgreSQLReactDocker
Visit OgroPath →
OgroPath platform
Social Impact Mission

"Growing up in rural Bangladesh, I witnessed the barriers to quality medical education. OgroPath removes these barriers by providing AI-powered, affordable exam preparation to aspiring medical students nationwide — making medical education accessible regardless of location or economic background."

06

Highlights

Competitions, recognition
& mentoring moments
BASIS Visit
Industry Networking

BASIS Visit

Professional visit to the Bangladesh Association of Software and Information Services.

Robi Axiata Recognition
Corporate Recognition

Robi Axiata

Recognized for exceptional performance and problem-solving skills.

AI Olympiad
AI Competition

AI Olympiad

Competing at the AI Olympiad, demonstrating cutting-edge ML expertise.

EDGE Project Training
AI Training Leadership

EDGE Project

Leading an AI training batch, mentoring 50+ students in ML/AI.

Research Presentation
Research Presentations

Conferences

Presenting at inter-university competitions and academic conferences.

Interview Panel
Interview Panel

Evaluator

Evaluating technical skills and mentoring future researchers.

07

Skills & Recognition

Technical depth ·
awards · teaching
Technical Skills

AMachine Learning & AI

Deep LearningGenerative AI (LLMs, RAG)AI AgentsComputer VisionNLPExplainable AI (XAI)Fairness in MLReinforcement Learning

BFrameworks & Libraries

PyTorchTensorFlowScikit-learnHugging FaceLangChainLlamaIndexOpenCVXGBoost

CMLOps & Production

DockerFastAPI / FlaskMLflowPinecone / ChromaDBPostgreSQL / pgvectorLinux

DResearch & Languages

Experimental DesignSystematic ReviewsScientific WritingPythonC++C
Awards & Honors
  • Employee of the Month — Primacy Infotech Ltd (Aug 2023)
  • 2nd Place — Inter-university Programming Contest, UITS (2022)
  • Fastest Problem Solver — UITS Victory Day Programming Contest (2021)
  • 1st Place — Inter-university PowerPoint Presentation Competition, UITS (2020)
Service & Teaching
  • Peer Reviewer — Informatics and Health (Elsevier), 2025–Present
  • Peer Reviewer — Int'l Journal of Human-Computer Interaction (Taylor & Francis, Q1), 2025–Present
  • AI Trainer — EDGE Project: trained 50+ students in ML/AI (2023)
  • Research Mentor — UITS Summer Research Program: 7 students, 1 paper accepted (2023 & 2024)
Teaching & Mentoring
50+
Students Trained
AI Trainer · EDGE Project
7
Research Students
UITS Summer Program
85%
Job Placement
EDGE Project Alumni
Education

B.Sc. in Computer Science & Engineering

University of Information Technology and Sciences (UITS)
Jan 2019 – Jun 2023
CGPA 3.62 / 4.00 — Ranked 6th in department
Thesis — A Multi-Disease Prediction Framework: Leveraging Machine Learning and Real-Time Applications for Improved Health Outcomes.
Standardized Tests
TOEFL98 / 120
IELTS6.5 / 9.0
GRE307 / 340Q153 · V154 · AWA 3.0
08

Writing

Notes on trustworthy
& fair medical AI
Cover coming soon
Trustworthy AIHealthcare

Why Accuracy Isn't Enough: The Case for Trustworthy Medical AI

A model can be 99% accurate and still fail the patients who need it most. How fairness, transparency, and reliability change what we build.

May 20266 min read →
Cover coming soon
Fairness MLOpen Source

Mitigating Demographic Bias in Clinical Models: Lessons from M-TRUST

Reducing demographic bias by 30.8% without sacrificing performance — across demographic, annotation, and amplification axes.

Mar 20268 min read →
Cover coming soon
LLMRAG

Grounding LLMs in Evidence: Building Citation-First Clinical RAG

A 'No Source, No Result' approach to retrieval — thematic clustering, NLI fact-checking, and source-level attribution for traceable answers.

Jan 20267 min read →
Cover coming soon
StoryImpact

From Rural Bangladesh to Production AI: Democratizing Healthcare

Why limited access to care shaped my research and led to founding OgroPath — and what accessibility-first AI really demands.

Nov 20255 min read →

More articles coming soon — covering trustworthy medical AI, fairness, and production ML.

Let's build trustworthy AI

Let's work together.

Open to research collaborations, PhD opportunities, and conversations about fair, production-grade AI in healthcare and beyond.

smnoyan670@gmail.com → Google Scholar LinkedIn GitHub OgroPath